# mcp-runtime-guard

> Use this tool when you need to enforce security rules and protect AI agents from unauthorized MCP tool calls. The mcp-runtime-guard intercepts and blocks calls based on YAML-defined policies, solving security and access control problems. It takes YAML policies as input and outputs blocked or allowed MCP tool calls, making it ideal for use cases where AI agent security is a top priority.

Canonical page: https://skillsregistry.net/skills/shuin-labs-mcp-runtime-guard  
JSON: https://api.skillsregistry.net/v1/skills/shuin-labs-mcp-runtime-guard

## Description

Runtime proxy that intercepts and blocks MCP tool calls based on YAML-defined policies, enforcing security rules for AI agents like Claude Code or Cursor.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/bql028q2bs)
- **Repository:** <https://github.com/Shuin-Labs/mcp-runtime-guard>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "shuin-labs-mcp-runtime-guard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/shuin-labs-mcp-runtime-guard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/shuin-labs-mcp-runtime-guard/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt